Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/plumpslabs/matchanpx agentmods add commands/plumpslabs/matcha/matcha-markersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/plumpslabs/matcha/matcha-markers)<a href="https://agentmods.dev/commands/plumpslabs/matcha/matcha-markers"><img src="https://agentmods.dev/badge/commands/plumpslabs/matcha/matcha-markers/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/plumpslabs/matcha/matcha-markers"><img src="https://agentmods.dev/badge/commands/plumpslabs/matcha/matcha-markers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00017 | $0.00415 |
| Opus 5.5 | $0.00007 | $0.00166 |
| Sonnet 5.5 | $0.00003 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
matcha:markers scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/matcha:markers
Scan for // matcha: markers and group by severity level.
Levels
| Marker | Level | Description |
|---|---|---|
// matcha:explain [reason] |
LOW | Documented shortcut — no action |
// matcha:todo [task] |
MEDIUM | Future task — schedule or track |
// matcha:debt [reason], [fix when] |
HIGH | Technical debt — must resolve |
// matcha:adr [ADR-NUMBER] |
INFO | Architecture decision reference |
Format Rules (enforced)
- Standard format only:
matcha:<type> <reason>— types:explain,todo,debt,adr. - English only: markers written in another language (e.g. Indonesian) are non-compliant. Rewrite:
// matcha:explain <english reason>. - Real reason: never leave a placeholder or empty marker.
The post-write hook flags non-English/placeholder markers, and the reviewer reports them as WARNING.
Usage
node bin/matcha.js markers
Or: /matcha:markers
Output
🍵 matcha: markers
Total: N markers
explain: N (LOW)
debt: N (HIGH) ← action needed
todo: N (MEDIUM)
adr: N (INFO)
HIGH items:
src/auth/login.ts:42 — workaround for legacy API
src/db/queries.ts:87 — N+1 query, refactor when migrating ORM
Run /matcha:debt for full debt report.
Purpose
Prevents marker drift. Run before commit to ensure all deliberate shortcuts are documented and no HIGH-debt items are forgotten.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 53 lines · 17 tokens per session scan A 014ccf1fb02e
matcha:markers is a command published in the GitHub repository plumpslabs/matcha (2 stars, last pushed 5d ago), licensed MIT. It adds 17 tokens to every session and 415 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
provenance
Mostra a cadeia completa de proveniência de um finding - source, commit SHA, age, confidence atual com decay, lifecycle status. Útil para auditar de onde veio uma afirmação na camada compilada.
risk
Mostra riscos conhecidos para um path - código frágil, sem testes, magic, debt. Use antes de mexer em arquivos críticos.
refactor-clean
Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.
debug
Systematic debugging with hypotheses and evidence gathering.
verify
An embedded-device verification workflow that checks a development step through building, flashing firmware, debugging with J-Link, and reading serial logs. Firmware is software that runs directly on a microcontroller or other device.
features
Mostra a matriz de features × status × evidência consolidada em 09-features/INDEX.md. Filtragem por status disponível.